29 36 85

Akarshan Biswas

qnixsynapse

qnixsynapse

AI & ML interests

NLP, models, quantization

Recent Activity

liked a model 8 days ago

cortexso/qwen3-deepresearch-nothink

liked a model 9 days ago

deepseek-ai/DeepSeek-R1-0528

new activity 16 days ago

ggml-org/gemma-3-12b-it-GGUF:Add "Image-Text-to-Text" label to gemma-3-12B

View all activity

Organizations

None yet

qnixsynapse's activity

New activity in ggml-org/gemma-3-12b-it-GGUF 16 days ago

Add "Image-Text-to-Text" label to gemma-3-12B

#2 opened 17 days ago by

qnixsynapse

New activity in ggml-org/gemma-3-27b-it-GGUF 17 days ago

Add "Image-Text-to-Text" label to Gemma-3-27B

#3 opened 17 days ago by

qnixsynapse

New activity in ggml-org/gemma-3-4b-it-GGUF 17 days ago

Add "Image-Text-to-Text" label to Gemma 3 4B

#1 opened 17 days ago by

qnixsynapse

New activity in google/gemma-2-9b-it 5 months ago

Tool calling support in Gemma 2

#50 opened 6 months ago by

qnixsynapse

New activity in huggingchat/chat-ui 10 months ago

[MODELS] Discussion

👍 ❤️ 38

788

#372 opened over 1 year ago by

victor

[TOOLS] Community Discussion

🔥 👀 3

#455 opened about 1 year ago by

victor

New activity in meta-llama/Llama-3.1-8B-Instruct 10 months ago

Wrong number of tensors; expected 292, got 291

#69 opened 10 months ago by

KingBadger

New activity in huggingchat/chat-ui 11 months ago

[FEATURE] Tools

🔥 ❤️ 78

#470 opened about 1 year ago by

victor

New activity in meta-llama/Llama-3.1-8B-Instruct 11 months ago

Utterly based

🚀 😎 8

#9 opened 11 months ago by

llama-anon

New activity in ggml-org/gguf-my-repo 11 months ago

Add IQ Quantization support with the help of imatrix and GPUs

👍 6

#35 opened about 1 year ago by

qnixsynapse

New activity in huggingchat/chat-ui 11 months ago

Suggestion: Host Gemma2 using keras_nlp instead of transformers library for the time being

#498 opened 11 months ago by

qnixsynapse

New activity in meta-llama/Meta-Llama-3-8B-Instruct about 1 year ago

The best 8B in the planet right now. PERIOD!

#22 opened about 1 year ago by

cyberneticos

New activity in mistral-community/Mixtral-8x22B-v0.1 about 1 year ago

How many active parameters does this model have?

#6 opened about 1 year ago by

lewtun

New activity in google/gemma-7b about 1 year ago

7B or 8B?

#24 opened over 1 year ago by

amgadhasan

New activity in huggingchat/chat-ui about 1 year ago

Which model is responsible for naming of the thread?

#402 opened about 1 year ago by

qnixsynapse

New activity in google/gemma-1.1-7b-it about 1 year ago

Number of parameters

#9 opened about 1 year ago by

HugoLaurencon

New activity in TheBloke/llama2_70b_chat_uncensored-GGML almost 2 years ago

Loading the model

#3 opened almost 2 years ago by

PyrroAiakid

New activity in TheBloke/Llama-2-70B-Chat-GGML almost 2 years ago

Looking for GGUF format for this model

#14 opened almost 2 years ago by

barha

New activity in TheBloke/Llama-2-13B-chat-GGML almost 2 years ago

Help needed to load model

😔 4

#13 opened almost 2 years ago by

sanjay-dev-ds-28

New activity in TheBloke/Llama-2-7B-32K-Instruct-GGML almost 2 years ago

Running Llama-2-7B-32K-Instruct-GGML with llama.cpp ?

#1 opened almost 2 years ago by

gsimard